Crypto Market Data

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, open-world, non-idempotent, non-destructive semantics, so the bar is lower. The description adds genuinely non-schema information: per-call pricing, the x402/USDC-on-Base payment requirement, and that failed calls are not charged — real operational context an agent must account for.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler: the contents come first, then cost/payment/failure policy. Every clause carries information an agent needs before invoking or budgeting the call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a multi-source composite tool with no output schema, the description enumerates what comes back and nails the billing model. It doesn't say how the data is structured (separate sections vs merged) or whether unavailable feeds null out or error, which would matter for a bundle like this.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter is already documented with an example (BTC). The description only reinforces 'one coin', adding no ticker formatting, casing, or exchange-scope detail beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb-and-resource framing ('Everything for one coin in one call') and enumerates the exact data bundled: price, funding/OI, order book, liquidations, whale orders, news. This makes it clearly distinguishable from the single-purpose siblings like prices, orderbook, liquidations, and news.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'one coin in one call' framing implicitly tells the agent to use this instead of fanning out across the individual sibling tools. It also gives a decisive usage condition via cost (USD 0.005) and payment rails, but gives no explicit when-not-to-use or pointer to the cheaper/free siblings like prices_free or sentiment_free.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations confirm this is a non-read-only, non-idempotent, open-world mutation, and the description adds substantial behavior: cost of USD 0.02 via x402 USDC on Base, no charge on failed requests, 24-hour lifetime, minute-level checks, signed webhook delivery, and the need to keep the returned secret for status and stop operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded: it states the core behavior first, then pricing, then the secret requirement. Every clause earns its place by adding actionable information about scope, billing, or follow-up usage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description covers what an agent needs: the watch duration, condition limit, firing behavior, webhook/status outcomes, cost and payment mechanism, failure billing, and the returned secret. The detailed input schema handles the parameter specifics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents label, format, conditions, and callback_url in detail. The description adds context about the 10-condition cap and metric categories, but most of that information is already available in the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (watch) and resource (crypto market conditions) with scope: 24 hours, up to 10 conditions, checked every minute. It clearly distinguishes this creation tool from watch_status and stop_watch, which it names as follow-up tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for using the tool: you create a 24-hour watch that fires a webhook or appears in status when a condition happens. It identifies watch_status and stop_watch as related tools, but it does not explicitly contrast this with one-off data siblings like prices or coin_snapshot.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), and the description adds genuinely useful context beyond them: a per-call price of USD 0.003, the x402/USDC-on-Base payment mechanism, and the failure-billing policy. It does not mention rate limits or response shape beyond the field list, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what data comes back, then the cost model. Every clause carries distinct information with no repetition of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the job of summarizing return content via its field list, and it discloses the paid-call model an agent must know before invoking. It could be more complete by noting response shape per token (object vs array) or whether omitted data is null, but the essentials are present for a one-optional-param read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single optional 'tokens' parameter already documents its comma-separated format, 50-item cap, and empty-means-top-50 default. The description adds nothing about the parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the exact derivative metrics returned (funding rate per 8h, futures premium, open interest with 1h/24h change, long/short ratio) and the per-coin scope, which clearly separates it from siblings like prices or sentiment. It lacks an explicit verb ('retrieves/returns'), but the resource is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the metric list — an agent can infer this is the tool for derivatives positioning data. There is no explicit when-to-use statement, no mention of when a sibling (e.g. prices_free, liquidations) is preferable, and no note on why one would choose the paid variant over free ones.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish that this is a read-only, non-destructive, open-world operation. The description adds meaningful behavioral context beyond annotations by disclosing the $0.01 per-call cost, the x402 USDC-on-Base payment mechanism, and that failed calls are not charged. It does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence that front-loads the report contents and then covers billing. It is efficient and avoids repetition, though the long list of features makes it slightly dense rather than perfectly scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description compensates by clearly listing the report's return contents, including positions, risk, PnL, volume, spot balances, and 24-hour trading. It also includes cost and billing behavior, leaving little ambiguity about what the agent will receive or pay.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single address parameter, and the schema itself specifies the expected 0x-prefixed 40-hex-character format. The description does not add any additional meaning or validation detail beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as an enriched Hyperliquid wallet report and enumerates the core contents: positions, risk, account value, PnL, volume, spot balances, and recent trading. That is far more specific than a tautology, but it does not explicitly compare itself with sibling tools such as derivatives, liquidations, or coin_snapshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool returns and its cost, but gives no guidance on when to choose it over alternatives. There are no exclusions, prerequisites, or named sibling alternatives, leaving the agent to infer usage from the tool name and report contents.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, open-world, non-idempotent, non-destructive behavior, so the bar is lower. The description adds genuinely new context: the fixed USD 0.003 per-call cost, x402/USDC-on-Base payment, and that failed calls aren't charged—material facts for an agent that might otherwise retry blindly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the first front-loads what the tool returns, the second front-loads the cost/payment model. No wasted clauses and nothing buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-output-schema tool, the description adequately describes the return shape (totals, per-coin longs/shorts, biggest ones) and time window. It could mention how the token filter interacts with the per-coin breakdown, but overall an agent has enough to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters (limit and token) are already documented in the input schema. The description adds no syntax or usage nuance beyond that, so the baseline 3 applies—the schema is doing the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (Binance futures liquidations) with explicit scope: last hour, 190+ coins, and the breakdown returned (totals, per-coin longs/shorts, biggest ones). This clearly distinguishes it from siblings like derivatives or whale_orders without needing to name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The data scope implies when the tool is appropriate (recent liquidation activity on Binance futures), and the pricing note hints at cost sensitivity. However, it never states when to prefer this over siblings like derivatives or whale_orders, nor any exclusions, so the agent must infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, non-destructive, open-world behavior; the description adds genuinely new context: aggregation across 31 sources, per-story computed fields, a per-call price of USD 0.003, the x402/USDC-on-Base payment rail, and the fact that failed calls are not charged. That billing-on-failure detail is exactly the kind of trait annotations cannot express; only the payment mechanics (e.g. whether a payment header must be supplied) remain vague.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler: the capability and its distinctive outputs come first, the cost/payment caveat second. Every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates the returned shape (impact score, outlet count, price reaction) and discloses cost, which is the main risk of an accidental call. Minor gaps remain around default result count when limit is omitted and what an unfiltered call returns, but nothing that would cause a wrong invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters (limit, token) are described in the schema, so the schema carries the semantics. The description adds no additional meaning about whether token filters to one asset or what omitting it returns — baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific resource and scope ('Top crypto stories now from 31 sources') and enumerates the distinctive fields returned (impact score, outlet count, price reaction), so an agent knows exactly what it gets. It never contrasts itself with adjacent siblings such as sentiment or sentiment_free, so differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the word 'now' — an agent can infer this is for current news rather than the sentiment or prices tools, but no explicit when-to-use or when-not-to-use guidance is given. The cost/payment sentence is an operating constraint, not selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious behavior: a per-call price of USD 0.003 paid via x402 USDC on Base, and that failed calls are not charged – material cost context an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, with the metric scope front-loaded before the cost caveat. Every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates what comes back and discloses payment mechanics, which is enough for a one-parameter read tool. Minor gaps remain around result shape (per-coin object structure) and whether the 15-minute window is fixed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single optional 'tokens' parameter is fully documented in the schema (comma-separated tickers, up to 50, empty means top 50). The description adds nothing about the parameter, which is acceptable at this coverage level but not above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource and enumerates the specific metrics returned: bid-ask spread, order-book imbalance, buyer share over the last 15 minutes, and volume versus normal, all per coin. That is concrete enough to separate it from siblings like prices, whale_orders, and liquidations without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the metric list – an agent can infer this is the tool for depth/flow analysis, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. prices for simple quotes). The billing note tells the agent about cost, not about tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, non-destructive, open-world behavior, and the description adds important operational context: minute-level refresh, per-call cost, x402/USDC payment, and that failed calls are not charged. It stops short of explaining payment setup or rate limits, but adds substantial value beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences front-load the data scope and then the cost/payment behavior. There is no redundant or filler text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read tool with no output schema, the description covers what data is returned, refresh cadence, universe size, cost, payment rail, and billing failure policy. An agent has enough information to call it and understand the charge implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single optional tokens parameter is fully documented in the schema, including comma-separated syntax and the empty-means-top-50 default. The description reinforces the top-50 scope but adds no parameter detail beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and scope: live prices for the top 50 crypto coins, with change intervals and volume. It is clearly a market-data read tool, though it does not explicitly name or distinguish itself from the sibling prices_free tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The paid cost is stated, which implies this is the paid alternative to a free tool, but the description never explicitly says when to use this versus prices_free or other siblings. Usage is inferable from the pricing model rather than directly guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover read-only and open-world status, but the description adds genuinely new behavioral context that annotations cannot convey: rate limiting (up to 30 calls/minute) and a 15-minute refresh cadence. It does not discuss pagination or error behavior, but for a simple quote lookup this is richer than typical.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences that front-load the free/rate-limited copy framing and then the contrast with the paid live tool. Every clause carries distinct information — staleness, rate limit, cost, and refresh frequency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only lookup with no output schema needed, the description supplies everything required to select and call it correctly: what it returns, how fresh it is, how fast it can be called, and what the alternative costs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — the single 'tokens' parameter is documented with format, example, and the 50-ticker cap. The description adds no parameter guidance beyond that, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states that this returns the same answer as the sibling 'prices' tool, which identifies the resource (price quotes) and its scope. It does not use an explicit verb like 'get' or 'list,' but the sibling reference and the 'free copy' framing make the function understandable at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The tradeoff against the sibling is spelled out clearly: 15-minute staleness and 30 calls/minute here versus live-per-minute data on 'prices' for USD 0.003. An agent can therefore choose between them by freshness and cost, though no explicit 'use this when' clause is present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish read-only, open-world, non-destructive behavior. The description adds genuinely new operational context: the per-call cost, that payment is via x402 with USDC on Base, and that failed calls are not charged — an agent-relevant billing/authorization detail. It does not explain why the tool is flagged non-idempotent (presumably live changing data), leaving that one hint unaddressed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler: what it returns first, commercial terms second. Every clause carries information the agent cannot get from schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so by naming the data components returned. It omits shape/format detail (e.g., whether the index is 0-100, how 'mood' and 'volatility regime' are expressed), but an agent can call it correctly with what is given.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single optional 'limit' parameter is fully documented in the schema at 100% coverage, including its 1-7 range and default. The description adds no meaning beyond that, which is acceptable given the schema does the work, but it does not connect 'trending coins' in the description to the limit parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the concrete payload: Fear and Greed index with prior value, trending coins, market breadth, mood, and volatility regime. That is far more specific than the bare name 'sentiment'. It does not, however, distinguish itself from sentiment_free, which is the most likely source of confusion among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the pricing statement (USD 0.003 per call, x402/USDC on Base), which hints this is the premium tier and that a free alternative exists. There is no explicit 'use this when...' or 'use sentiment_free instead when...' guidance, so the agent must infer the trade-off.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, it adds useful behavioral context: 15-minute cache freshness, a 30 calls/minute limit, and free cost. It does not cover auth needs or exact caching semantics, but it meaningfully supplements the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loading the free cached positioning and then the freshness/cost tradeoff. Every clause carries useful selection information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, read-only tool with one optional parameter, annotations, and no output schema, the description provides enough operational context about freshness, rate limits, cost, and the alternative. What 'sentiment' actually returns is delegated to the sibling tool rather than explained here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents the only parameter, limit, including its 1-7 range and default of 7 at 100% coverage. The description adds no parameter-specific meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Identifies the tool as the free cached counterpart to sentiment and distinguishes it from that sibling through refresh cadence, rate limit, and cost. It never explicitly says what the returned sentiment data contains, so it is clear in context but not fully self-contained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Contrasts this free 15-minute cached copy with sentiment's live per-minute paid data, giving the agent the tradeoff needed to choose between them. There is no explicit 'use when' imperative or stated exclusion, but the alternative and conditions are clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and destructiveHint=false, so the safety profile is covered. The description adds that the call is free and that it returns pricing/payment information, but does not explain response shape or why idempotentHint is false for a static info lookup.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the 'Free' qualifier first and no filler. The sentence is slightly elliptical ('what this server offers' without a subject) but every clause is informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-parameter, no-output-schema metadata tool, stating that it returns offerings, per-tool pricing, and payment mechanics is sufficient for an agent to decide to call it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Zero parameters, so there is nothing the description needs to compensate for; the empty schema is self-explanatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource: what the server offers, the price of each tool, and how payment works. That is concrete and distinguishable from data-returning siblings like prices or sentiment, though it never names those siblings or says explicitly that this is a metadata/discovery tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Free:' prefix implies this is a zero-cost discovery call that should precede paid tools, but no when-to-use condition or alternative is stated. Usage is inferable rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations, it discloses that stopping is free, irreversible, stops webhooks, is idempotent, and requires credentials returned by create_watch. These details add meaningful behavioral context for a destructive mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded, starting with the cost and core action before consequences and requirements. Every sentence contributes useful information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, and the description explains the return value as watch_id with status stopped. Annotations cover the safety profile, and the description completes the lifecycle and credential context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented in the schema. The description reinforces that watch_id and secret come from create_watch, but it adds little beyond the schema's own parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: it ends a watch created by create_watch. It clearly distinguishes stopping from creating and checking a watch, and the 24-hour lifecycle context is explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly describes when to use the tool: to end a watch before its 24-hour lifetime expires and stop further checks and webhooks. It also explains idempotent behavior, but it does not explicitly name watch_status or other alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only, non-destructive profile, and the description still adds substantial context: it is free, it returns status (active/expired/stopped), conditions, last-checked time, fire count, and the last 20 fires including webhook delivery outcome, and it discloses the auth failure behavior. That is well beyond what the annotations convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The return payload is front-loaded in a single dense sentence and cost ('Free') comes first. It is slightly run-on with the long enumeration of fire fields, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so enumerating returned fields is essential and it does so thoroughly, including the 20-fire history and webhook delivery status. Auth requirements and failure modes are also covered, leaving nothing an agent needs before calling it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and already explains both parameters, so the baseline is 3. The description adds value by tying the secret to create_watch and explaining the error semantics for a wrong secret or unknown id, which the schema does not state.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Reads one watch made with create_watch') and immediately scopes it to a single watch rather than a list. This cleanly separates it from create_watch and stop_watch among the siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly ties usage to a watch created by create_watch and states that watch_id and secret from that call are required, plus the error case for unknown id or wrong secret. It stops short of explicitly naming alternatives (e.g. 'use stop_watch to stop, create_watch to create'), but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description adds important behavioral context: per-call cost, payment via x402 with USDC on Base, and that failed calls are not charged. It does not cover rate limits, latency, or freshness guarantees, but it significantly reduces uncertainty for a paid read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences: the first front-loads the purpose and scope, and the second delivers cost and payment behavior. There is no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only data retrieval tool with no output schema, the description does a good job covering sources, timeframe, Hyperliquid detail, and payment behavior. It could be stronger by saying more about the returned shape or default limit behavior, but the essential context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents limit and token. The description does not add syntax, defaults, or interpretation beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (biggest market orders), a clear time window (last hour), and named venues (Binance futures, Binance spot, Hyperliquid), plus the Hyperliquid execution detail. This is enough to distinguish it from siblings like orderbook, liquidations, and prices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the purpose and cost note, but the description does not explicitly say when to use this tool versus alternatives such as orderbook or prices_free. It gives useful cost context but no exclusions or explicit alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.